publications

2026

1. Semantic Visual Representations Emerge from Embodied Self-Supervised Learning.

   Arthur Aubret, Céline Teulière, Timothy Schaumlöffel, and 2 more authors

   Under review in Nature Communications, 2026
2. Toddlers’ Active Gaze Behavior Supports Self‐Supervised Object Learning

   Zhengyang Yu, Arthur Aubret, Marcel C. Raabe, and 3 more authors

   Developmental Science, Jul 2026

   Abs DOI

   ABSTRACT Toddlers learn to recognize objects from different viewpoints with almost no supervision. During this learning, they execute frequent eye and head movements that shape their visual experience. It is presently unclear if and how these behaviors contribute to toddlers’ emerging object recognition abilities. To answer this question, we here combine head‐mounted eye tracking during dyadic play with unsupervised machine learning. We approximate toddlers’ central visual field experience by cropping image regions from a head‐mounted camera centered on the current gaze location estimated via eye tracking. This visual stream feeds a neural network model, which uses a biologically plausible unsupervised learning objective. Our experiments demonstrate that a few minutes of such first‐person experience suffice to learn strong object representations permitting invariant object recognition. Importantly, by simulating alternative gaze behaviors we show that toddlers’ eye movement patterns play a crucial role in this. Our analysis also reveals that the limited size of the central visual field where visual acuity is high plays an important role for successful learning. Together, this highlights the benefits of temporally structured visual experience arising from toddlers’ natural interactions with objects. Summary We combine recordings of toddlers’ first‐person central visual field experience with biologically inspired self‐supervised learning algorithms to model toddlers’ development of invariant object recognition. Just a few minutes of toddlers’ central visual field experience captured with head‐mounted eye tracking suffice to learn strong object representations. Simulated alternative gaze behaviors produce weaker representations, demonstrating the importance of toddlers’ active gaze strategies for learning. Our results emphasize the importance of toddlers’ eye movements for learning object representations.

3. Re‐assessing the Evidence for MR Abilities in Children Using Computational Models

   Arthur Aubret and Jochen Triesch

   Developmental Science, Jul 2026

   Abs DOI

   ABSTRACT There is strong and diverse evidence for mental rotation (MR) abilities in adults. However, current evidence for MR in children rests on just a few behavioral paradigms adapted from the adult literature. Here, we leverage recent computational models of the development of children’s object recognition abilities to re‐assess the evidence for MR in children. The computational models simulate infants’ acquisition of object representations during embodied interactions with objects. We consider two different object recognition strategies, different from MRs, and assess their ability to replicate results from three classical MR tasks assigned to children between the ages of 6 months and 5 years. Our results show that MR may play no role in producing the results obtained from children younger than 5 years. In fact, we find that a simple recognition strategy that reflects a pixel‐wise comparison of stimuli is sufficient to model children’s behavior in the most used MR task. Thus, our study reopens the debate on how and when children develop genuine MR abilities. Summary We use a bio‐inspired machine learning models to examine evidence of mental rotation abilities in children We show that a simple recognition strategy suffices to solve habituation‐based tasks used to assess mental rotations in young children. We demonstrate that a model forming expectations about a rotation transformation can explain children’s results in mental rotation tasks with the violation‐of‐expectation paradigm. The investigated recognition strategies no longer work when the mental rotation tasks are made closer to adults’.

4. Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics

   Arthur Aubret, Jochen Triesch, and Céline Teulière

   In , Sep 2026

   Abs

   Self-Supervised Learning (SSL) has achieved impressive success in learning semantic visual representations, yet the underlying principles driving this success remain underexplored. In this work, we hypothesize that common SSL pretext tasks implicitly model object co-occurrence statistics, a fundamental cue for visual learning. To test this, we curate three datasets of segmented objects from existing vision benchmarks using a state-of-the-art segmentation model. Through experiments across many SSL models, we reveal a hierarchical encoding of semantic information: while the visual backbone captures object categories, the projection head specializes in encoding co-occurrences between object categories. As a result, the projection head outperforms the backbone in aligning with human judgments of inter-category similarity. Furthermore, by controlling co-occurrence patterns during pre-training, we demonstrate that encoding object co-occurrences can significantly accelerate the emergence of category-level representations. Our findings uncover a previously hidden learning principle in SSL and suggest a path toward designing more effective pretext tasks by explicitly leveraging object co-occurrence structure.

5. Seeing the whole in the parts with self-supervised representation learning

   Arthur Aubret, Céline Teulière, and Jochen Triesch

   Neurocomputing, 2026

2025

1. Self-supervised Visual Learning from Interactions with Objects

   Arthur Aubret, Céline Teulière, and Jochen Triesch

   In Computer Vision – ECCV 2024, 2025

   Series Title: Lecture Notes in Computer Science

   DOI
2. Simulated Cortical Magnification Supports Self-Supervised Object Learning

   Zhengyang Yu, Arthur Aubret, Chen Yu, and 1 more author

   In 2025 IEEE International Conference on Development and Learning (ICDL), 2025
3. Do vision models perceive objects like toddlers?

   Arthur Aubret and Jochen Triesch

   In The Fourth Blogpost Track at ICLR 2025, 2025
4. Temporal Slowness in Central Vision Drives Semantic Object Learning

   Timothy Schaumlöffel, Arthur Aubret, Gemma Roig, and 1 more author

   In , Oct 2025

   Abs

   Humans acquire semantic object representations from egocentric visual streams with minimal supervision, but the underlying mechanisms remain unclear. Importantly, the visual system only processes the center of its field of view with high resolution and it learns similar representations for visual inputs occurring close in time. This emphasizes slowly changing information around gaze locations. This study investigates the role of central vision and slowness learning in the formation of semantic object representations from human-like visual experience. We simulate five months of human-like visual experience using the Ego4D dataset and a state-of-the-art gaze prediction model. We extract image crops around predicted gaze locations to train a time-contrastive Self-Supervised Learning model. Our results show that exploiting temporal slowness when learning from central visual field experience improves the encoding of different facets of object semantics. Specifically, focusing on central vision strengthens the extraction of foreground object features, while considering temporal slowness, especially in conjunction with eye movements, allows the model to encode broader semantic information about objects. These findings provide new insights into the mechanisms by which humans may develop semantic object representations from natural visual experience. Our code will be made public upon acceptance. Code is available at https://github.com/t9s9/central-vision-ssl.

2024

1. Self-Supervised Learning of Color Constancy

   Markus R. Ernst, Francisco M. López, Arthur Aubret, and 2 more authors

   In 2024 IEEE International Conference on Development and Learning (ICDL), 2024
2. Learning object semantic similarity with self-supervision

   Arthur Aubret, Timothy Schaumlöffel, Gemma Roig, and 1 more author

   In 2024 IEEE International Conference on Development and Learning (ICDL), 2024
3. MIMo: A Multimodal Infant Model for Studying Cognitive Development

   Dominik Mattern, Pierre Schumacher, Francisco M. López, and 4 more authors

   IEEE Transactions on Cognitive and Developmental Systems, 2024

2023

1. Caregiver talk shapes toddler vision: A computational study of dyadic play

   Timothy Schaumlöffel, Arthur Aubret, Gemma Roig, and 1 more author

   In 2023 IEEE International Conference on Development and Learning (ICDL), 2023
2. Distop: Discovering a topological representation to learn diverse and rewarding skills

   Arthur Aubret, Laetitia Matignon, and Salima Hassas

   IEEE Transactions on Cognitive and Developmental Systems, 2023
3. An information-theoretic perspective on intrinsic motivation in reinforcement learning: A survey

   Arthur Aubret, Laetitia Matignon, and Salima Hassas

   Entropy, 2023

2022

1. An information-theoretic perspective on intrinsic motivation in reinforcement learning

   Arthur Aubret, Laetitia Matignon, and Salima Hassas

   In NeurIPS 2022 Workshop on Information-Theoretic Principles in Cognitive Systems, 2022
2. Compressed information is all you need: unifying intrinsic motivations and representation learning

   Arthur Aubret, Mathieu Lefort, Céline Teulière, and 3 more authors

   In NeurIPS 2022 Workshop on Information-Theoretic Principles in Cognitive Systems, 2022
3. Toddler-inspired learning induces hierarchical object representations

   Arthur Aubret, Céline Teulière, and Jochen Triesch

   In IEEE ICDL-Sensorimotor Interaction, language, and Embodiement of Symbols (SMILES) workshop, 2022
4. Toddler-inspired embodied vision for learning object representations

   Arthur Aubret, Céline Teulièr, and Jochen Triesch

   In 2022 IEEE International Conference on Development and Learning (ICDL), 2022
5. Mimo: A multi-modal infant model for studying cognitive development in humans and ais

   Dominik Mattern, Francisco M. López, Markus R. Ernst, and 2 more authors

   In 2022 ieee international conference on development and learning (icdl), 2022
6. Time to augment self-supervised visual representation learning

   Arthur Aubret, Markus R. Ernst, Céline Teulière, and 1 more author

   In The Eleventh International Conference on Learning Representations, Sep 2022

   Abs

   Biological vision systems are unparalleled in their ability to learn visual representations without supervision. In machine learning, self-supervised learning (SSL) has led to major advances in forming object representations in an unsupervised fashion. Such systems learn representations invariant to augmentation operations over images, like cropping or flipping. In contrast, biological vision systems exploit the temporal structure of the visual experience during natural interactions with objects. This gives access to “augmentations” not commonly used in SSL, like watching the same object from multiple viewpoints or against different backgrounds. Here, we systematically investigate and compare the potential benefits of such time-based augmentations during natural interactions for learning object categories. Our results show that incorporating time-based augmentations achieves large performance gains over state-of-the-art image augmentations. Specifically, our analyses reveal that: 1) 3-D object manipulations drastically improve the learning of object categories; 2) viewing objects against changing backgrounds is important for learning to discard background-related information from the latent representation. Overall, we conclude that time-based augmentations during natural interactions with objects can substantially improve self-supervised learning, narrowing the gap between artificial and biological vision systems.

2021

1. Learning increasingly complex skills through deep reinforcement learning using intrinsic motivation

   Arthur Aubret

   2021
2. ELSIM: End-to-End Learning of Reusable Skills Through Intrinsic Motivation

   Arthur Aubret, Laetitia Matignon, and Salima Hassas

   In Machine Learning and Knowledge Discovery in Databases, 2021

   Series Title: Lecture Notes in Computer Science

   DOI

2019

1. Étude de la motivation intrinsèque en apprentissage par renforcement

   Arthur Aubret, Laëtitia Matignon, and Salima Hassas

   In Journées Francophones sur la Planification, la Décision et l’Apprentissage pour la conduite de systèmes, 2019